Llemma 7B is a language model for mathematics. It was initialized with Code Llama 7B weights, and trained on the Proof-Pile-2 for 200B tokens. Llemma models are particularly strong at chain-of-thought mathematical reasoning and using comput…
Model details →EleutherAI: Llemma 7b vs SorcererLM 8x22B
EleutherAI: Llemma 7b wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
SorcererLM is an advanced RP and storytelling model, built as a Low-rank 16-bit LoRA fine-tuned on [WizardLM-2 8x22B](/microsoft/wizardlm-2-8x22b). - Advanced reasoning and emotional intelligence for engaging and immersive interactions - V…
Model details →Side-by-side comparison
| Capability | EleutherAI: Llemma 7b | SorcererLM 8x22B | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 4K | 16K | 🏆 SorcererLM 8x22B |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.80 | $4.50 | 🏆 EleutherAI: Llemma 7b |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $1.20 | $4.50 | 🏆 EleutherAI: Llemma 7b |
| Tool / function calling First-class support for emitting structured tool calls. | — | — | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is EleutherAI: Llemma 7b better than SorcererLM 8x22B?
EleutherAI: Llemma 7b wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between EleutherAI: Llemma 7b and SorcererLM 8x22B?
Input: $0.80 vs $4.50 per 1M tokens. Output: $1.20 vs $4.50 per 1M tokens.
What context windows do EleutherAI: Llemma 7b and SorcererLM 8x22B support?
EleutherAI: Llemma 7b supports up to 4K tokens. SorcererLM 8x22B supports up to 16K tokens.
Do both EleutherAI: Llemma 7b and SorcererLM 8x22B support tool calling?
EleutherAI: Llemma 7b: not advertised. SorcererLM 8x22B: not advertised.