FitMyLLM
▸ INTEL· GENERATION 12.1

Intel H3C XG310

VRAM
8 GB
ENTRY-LEVEL
BANDWIDTH
68
GB/S
MODELS Q4
220/449
49%
7B Q4 SPEED
~3
SLOW
▸ MODEL COVERAGE @ Q449% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
~7
TOK/S
7B
~3
TOK/S
14B
—
7.9GB NEEDED
32B
—
18.0GB NEEDED
70B
—
39.4GB NEEDED
▸ SPECIFICATIONS
VRAM
8 GB
BANDWIDTH
68 GB/s
FP16 COMPUTE
3.4 TFLOPS
TDP
300W
MEMORY
LPDDR4X
ARCHITECTURE
Generation 12.1
COMPUTE UNITS
48
PCIE
Gen 3 x16
22
FAST MODELS · >30 TOK/S
Real-time chat speed
62
USABLE · >10 TOK/S
Comfortable for all tasks
220
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test H3C XG310 (or anything bigger) without committing. Pay by the second, cancel anytime.

Rent on Vast.ai →Or RunPod →

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

▸ COMPATIBLE MODELS· 220
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
242
TOK/S · 7% VRAM
›
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
161
TOK/S · 7% VRAM
›
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
155
TOK/S · 7% VRAM
›
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
155
TOK/S · 7% VRAM
›
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
85
TOK/S · 8% VRAM
›
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
81
TOK/S · 8% VRAM
›
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
71
TOK/S · 8% VRAM
›
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
65
TOK/S · 9% VRAM
›
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
65
TOK/S · 9% VRAM
›
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
65
TOK/S · 9% VRAM
›
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
62
TOK/S · 9% VRAM
›
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
60
TOK/S · 9% VRAM
›
A
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
57
TOK/S · 9% VRAM
›
A
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
44
TOK/S · 10% VRAM
›
A
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
44
TOK/S · 10% VRAM
›
A
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
42
TOK/S · 10% VRAM
›
B
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
38
TOK/S · 10% VRAM
›
B
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
38
TOK/S · 10% VRAM
›
B
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
36
TOK/S · 11% VRAM
›
B
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
36
TOK/S · 11% VRAM
›
B
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
36
TOK/S · 11% VRAM
›
B
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
35
TOK/S · 11% VRAM
›
B
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
29
TOK/S · 12% VRAM
›
B
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
29
TOK/S · 12% VRAM
›
B
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
27
TOK/S · 12% VRAM
›
B
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
25
TOK/S · 13% VRAM
›
C
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
23
TOK/S · 13% VRAM
›
C
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
20
TOK/S · 15% VRAM
›
C
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
20
TOK/S · 14% VRAM
›
C
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
18
TOK/S · 15% VRAM
›
C
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
18
TOK/S · 15% VRAM
›
C
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
18
TOK/S · 15% VRAM
›
C
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
18
TOK/S · 15% VRAM
›
C
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
17
TOK/S · 16% VRAM
›
C
OPT 1.3B1.3B
OPT·2K CTX· CHAT
17
TOK/S · 16% VRAM
›
C
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
17
TOK/S · 16% VRAM
›
C
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
16
TOK/S · 16% VRAM
›
C
LFM2 8B A1B8.3BMoE
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
15
TOK/S · 70% VRAM
›
C
granite-4.0-h-tiny 6.9B6.9BMoE
GRANITE·128K CTX· CHAT
15
TOK/S · 59% VRAM
›
C
Qwen2.5-Coder-1.5B1.5B
QWEN·32K CTX· CHAT· TOOL_USE· CODING
15
TOK/S · 18% VRAM
›
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your H3C XG310.

▸Find models for H3C XG310Compare with other GPUs
▸ DEVICE UNDER TEST

Intel H3C XG310 — 8 GB VRAM.

▸ H3C XG310 SPEC
BRAND
Intel
VRAM
8 GB LPDDR4X
BANDWIDTH
68 GB/s
FP16 COMPUTE
3.4 TFLOPS
FP32 COMPUTE
1.7 TFLOPS
TDP
300 W
ARCHITECTURE
Generation 12.1
▸ AI CAPABILITY
220/ 449 models @ Q4

With 8 GB VRAM and 68 GB/s bandwidth, this GPU handles models up to 10.7B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~8 tok/s.

§ 01TOP MODELS FOR H3C XG310
220 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
SOLAR-10.7B10.7B7.0 GB228.2
Falcon3-10B10.3B6.8 GB238.2
GLM-4.1V 9B Thinking10.29B6.8 GB2—
Bamba 9B v29.78B6.5 GB226.1
Qwen 3.5 9B9.65B6.4 GB250.6
RecurrentGemma 9B9.63B6.4 GB235.0
glm-4-9b9.4B6.2 GB220.5
MiniCPM-o 4.59.37B6.2 GB2—
gemma-2-9b9.2B6.1 GB230.2
Yi 1.5 9B9B6.0 GB230.3
Yi Coder 9B9B6.0 GB235.8
Ministral 3 8B8.92B5.9 GB225.7
Ministral 3 8B Reasoning8.92B5.9 GB2—
NVIDIA-Nemotron-Nano-9B-v28.9B5.9 GB244.2
InternLM3 8B Instruct8.8B5.9 GB238.7
Qwen3-VL 8B Instruct8.77B5.8 GB226.4
MiniCPM-V 4.58.7B5.8 GB326.1
MiniCPM-o 2.68.67B5.8 GB340.3
Gemma 1 7B8.54B5.7 GB324.7
CodeGemma 7B8.54B5.7 GB340.2